低信噪比下采用感知语谱结构边界参数的语音端点检测算法

提出了一种采用感知语谱结构边界参数(PSSB)的语音端点检测算法,用于在低信噪比环境下的语音信号预处理。在对含噪语音进行基于听觉感知特性的语音增强之后,针对语音信号的连续分布特性与残留噪声的随机分布特性之间的不同点,对增强后语音的时-频语谱进行二维增强,从而进一步突出连续分布的纯净语音的语谱结构。通过对增强后语音语谱结构的二维边界检测,提出PSSB参数,并用于端点检测。实验结果表明,在白噪声-10 dB到10 dB的各种信噪比环境下,采用PSSB参数的端点检测算法,相对于其它端点检测算法,更有效地检测出语音的端点。在-10 dB的极低信噪比下,提出的方法仍然有75.2%的正确率。采用PSSB参数的端点检测算法,更适合于低信噪比白噪声环境下的语音端点检测。      

感知听觉场景分析的说话人识别

针对低信噪比说话人识别中缺失数据特征方法鲁棒性下降的问题,提出了一种采用感知听觉场景分析的缺失数据特征提取方法。首先求取语音的缺失数据特征谱,并由语音的感知特性求出感知特性的语音含量。含噪语音经过感知特性的语音增强和对其语谱的二维增强后求解出语音的分布,联合感知特性语音含量和缺失强度参数提取出感知听觉因子。再结合缺失数据特征谱把特征的提取过程分解为不同听觉场景进行区分地分析和处理,以增强说话人识别系统的鲁棒性能。实验结果表明,在-10 dB到10 dB的低信噪比环境下,对于4种不同的噪声,提出的方法比5种对比方法的鲁棒性均有提高,平均识别率分别提高26.0%,19.6%,12.7%,4.6%和6.5%。论文提出的方法,是一种在时-频域中寻找语音鲁棒特征的方法,更适合于低信噪比环境下的说话人识别。      

噪声环境中的汉语浊语音检测

为了在低信噪比和复杂噪声环境下检测汉语浊语音,根据浊语音谐波结构特性,提出了一种鲁棒的浊语音检测方法。通过改进的谱跟踪算法,得到能表征浊语音谐波特性的一簇谱线;从谱线簇中提取谐波特征作为汉语浊语音检测的依据。在不同信噪比和不同噪声环境下的浊语音检测对比实验中全面优于传统方法,在0 dB信噪比时正识率高于传统方法约30%。实验结果表明,该方法在低信噪比和非平稳复杂噪声环境下都具有较好的浊语音检测效果。      

基于Seneff听觉谱特征的汉语连续语音声韵母边界检测

提出了一种基于声韵母能量分布和共振峰结构特性的汉语连续语音声韵母边界检测方法。该方法首先将语音经过Seneff听觉感知模型得到听觉谱,然后基于听觉谱,选取全频带能量、低频带能量、谱重心、高低频能量比、中高频能量等特征参数对各声韵母类别能量分布和共振峰结构特性进行描述,最后根据特征参数变化剧烈的点确定出声韵母边界,并采用包络的一阶差分和基于样点的Kullback-Leibler距离对得到的边界进行修正。实验结果表明,对8 kHz采样的语音边界检测准确率可达到93.7%;信噪比10dB的语音边界检测准确率可达到85.3%以上;经过参数编码后语音边界检测准确率可达86 7%以上。      

A speech enhancement method based on Kalman filtering

I.IntroductionKa1manfilteringisjustamethodtoestimatestatistica1lythestateoftheobservedsystemfromthecorruptedsigna1s,andthiskindofcstimationisarecurrcneeestimationbasedon1inear,nonbiasandminimumvariance.Moreover,Ka1manfilteringisapplicabletonon-sta-honarysignalsandtime-variantdynamicsystem.Therefore,Kalmanfilteringisveryapplica-bletoenhancingthespeechsigna1sthatarecorruptedbynoise.ThispaperreportStheconcretcmethodofenhanccmentofnoisyspccchanditscxperimentresults.Experimentsindicate:Afterthes…     

Intelligibility enhancement for noisy whispered speech using asymmetric cost function

We proposed two whispered speech enhancement methods based on asymmetric cost functions in this paper to deal with the amplification and attenuation distortions of whispered speech distinctively.The modified Itakura-Saito（MIS）distance function provides more penalties to speech amplification distortion,whereas the Kullback-Leibler（KL）divergence function gives more penalties to speech attenuation distortion.The experimental results show that the MIS function based method achieves significant improvement of intelligibility in contrast to the conventional speech enhancement algorithms when the signal-to-noise ratio（SNR）falls below-6 dB,whereas the KL function based one achieves the similar result as the minimum mean square error（MMSE）speech enhancement method.The results show that the effects of the amplification and attenuation distortions on the intelligibility of the enhanced whisper are different,where larger attenuation distortion may result in better intelligibility of speech with low SNR.However,the attenuation distortion has small effects on intelligibility of speech with high SNR.     

一种基于奇异谱的语音激活检测方法

为了提高语音激活检测在低信噪比环境中的检测性能,提出了一种基于奇异谱的语音激活检测方法。首先用多窗口方法计算每一帧语音信号的相关矩阵;然后对相关矩阵进行奇异值分解;利用奇异值可以反映有用信号和噪声分布情况的特性,将每一帧语音信号经过加权处理后的最大奇异值与自适应阈值进行比较进行语音激活检测。该方法原理简单,易于硬件实现,通过实验仿真表明,在低信噪比环境下,和基于对数能量方法相比,本文方法也能够很好的区分语音段和非语音段,有良好的检测性能。     

听觉频域掩蔽效应的自适应β阶贝叶斯感知估计语音增强算法

为了在噪声抑制和语音失真中之间寻找最佳平衡,提出了一种听觉频域掩蔽效应的自适应β阶贝叶斯感知估计语音增强算法,以期提高语音增强的综合性能。算法利用了人耳的听觉掩蔽效应,根据计算得到的频域掩蔽阈自适应调整β阶贝叶斯感知估计语音增强算法中的β值,从而仅将噪声抑制在掩蔽阈之下,保留较多的语音信息,降低语音失真。并分别用客观和主观评价方式,对所提出的算法的性能进行了评估,并与原来基于信噪比的自适应β阶贝叶斯感知估计语音增强算法进行了比较。结果表明,频域掩蔽的β阶贝叶斯感知估计方法的综合客观评价结果在信噪比为-10 dB至5 dB之间时均高于基于信噪比的自适应β阶贝叶斯感知估计语音增强算法。主观评价结果也表明频域掩蔽的β阶贝叶斯感知估计方法能在尽量保留语音信息的同时,较好的抑制背景噪声。      

滑动窗累积量的递推估计算法及其在语音端点检测中的应用

提出了一种滑动窗累积量的递推估计算法并应用于语音端点检测中,用以解决传统端点检测方法在噪声环境下检测性能变差的问题。在对含噪语音信号进行加窗之后,利用滑动窗累积量的递推估计算法估计含噪语音信号的高阶累积量值,并在此基础上结合能量特征进行语音端点检测。实验结果表明,所提滑动窗累积量递推估计算法相比较传统高阶累积量计算方法运算效率明显提高;所提端点检测算法在不同噪声和信噪比环境下相比较G.729b算法点正确率Pc-point值平均提升了6.07%。基于滑动窗高阶累积量的语音端点检测算法具有较高的运算效率及良好的鲁棒性。      

提高耳语音可懂度的非对称压缩语音增强方法

提出两种基于非对称代价函数的耳语音增强算法,将语音增强过程中的放大失真和压缩失真区分对待。Modified ItakuraSaito (MIS)算法对放大失真给予更多的惩罚,而Kullback-Leibler (KL)算法则对压缩失真给予更多的惩罚。实验结果表明,在低于—6 dB的低信噪比情况中,经MIS算法增强后的耳语音的可懂度相比传统算法有显著提高;而KL算法则获得了同最小均方误差语音增强算法近似的可懂度提高效果,证实了耳语音中的放大失真和压缩失真对于耳语音可懂度的影响并不相同,低信噪比时较大的压缩失真有助于提高耳语音可懂度,而高信噪比时的压缩失真对耳语音可懂度影响较小。      

Acoustic recognition of voice disorders: a comparative study of running speech versus sustained vowels

The signals of running speech and sustained vowels of normals and subjects suffering from dysphonia were analyzed statistically with respect to the signal-to-noise ratio (SNR). The distribution of the SNR measured in multiple overlapping frames in the speech signal was described by a linear combination of the distribution frequencies for SNR = 0 dB, 0 dB less than SNR less than 15 dB, and SNR greater than or equal to 15 dB. The values of the linear combination, the SNR of the vowels, and clinical assignment of the voices to normal and pathologic populations based on laryngoscopic and stroboscopic investigation parameters were used to compare the different evaluations of the voices. The SNR distribution in speech remained stable over signal lengths of more than 30 s. The correlation coefficient between the SNR measure for running speech and the SNR of sustained vowels amounted to only 0.63. The error rate in the discrimination between normal and dysphonic voices amounted to 22.6% in application to sustained vowels and 5.6% when the SNR distribution was used. Possible reasons for the observed discrepancies are discussed, and the results are compared to those of other studies.     

Multi component LFM signal detection and parameter estimation based on EEMD–FRFT

This paper studied multi component LFM signal detection and parameter estimation under the noise circumstance of various signal-to-noise ratios. Based on the analysis of fractional Fourier transform detection and parameter estimation on simple component LFM signal, this paper proposed the method of multi component LFM signal detection and parameter estimation based on EEMD–FRFT (Ensemble Empirical Mode Decomposition–Fractional Fourier transform), and this method was that with the EEMD algorithm, from the frequency domain decompose the analyzable signal to narrow-bandwidth components, whose center frequency changed from high to low, then accurately estimate the parameter and detect the signal of each component out of the pseudo-component with FrFT. This method solved the problem of mode aliasing of signal decomposition; meanwhile, the problem of detecting the multi component LFM signal would be simplified as the problem of one-dimensional search in small scope, which could reduce the amount of operation and improved the detection accuracy. A simulation computation for multi component LFM signal of various SNR (signal-to-noise ratios) was made and the result showed that the error of parameter estimation was less than 5% in the case of SNR not less than −10 dB.     

结合卷积神经网络的浅海有源探测信道匹配

信道匹配方法在有源探测领域是一种重要的提升检测信噪比的方法。针对非确知海底参数环境下的有源探测信道匹配问题,提出一种结合卷积神经网络进行信道匹配的算法。该算法基于海底参数扰动开展声场仿真生成卷积网络训练数据;首先通过分类网络将信号按照海底底质类型分类,在每个分类区间内采用单独的卷积网络反演海底参数;然后结合声场模型估计信道传递函数,进行信道匹配,从而在非确知环境下抑制多途影响,提升回波检测能力。仿真与实验结果表明,该算法能够在不确知海底环境条件下,有效估计信道传递函数,实现信道最优化匹配,在实验条件下可提高回波检测信噪比4 dB左右。相比传统方法,该算法可以在海底参数不确知条件下对低接收信噪比的信号实现信道匹配,同时不需要高信噪比的实验参考信号,有效提高了信道匹配方法的环境宽容性。      

基于听觉事件检测的汉语语音声韵切分

提出了一种基于听觉事件检测的汉语声韵母切分方法。该方法首先使用耳蜗滤波器组对语音进行滤波,然后在每个频带上检测对应于能量突变的听觉事件,最后在不同频率范围对听觉事件进行融合以确定声韵母边界。实验结果表明,对8 kHz采样的干净语音切分准确率可达到88.9%;信噪比10 dB的语音切分准确率可达到82.9%以上。      

Spectro-temporal modulation energy based mask for robust speaker identification

Spectro-temporal modulations of speech encode speech structures and speaker characteristics. An algorithm which distinguishes speech from non-speech based on spectro-temporal modulation energies is proposed and evaluated in robust text-independent closed-set speaker identification simulations using the TIMIT and GRID corpora. Simulation results show the proposed method produces much higher speaker identification rates in all signal-to-noise ratio (SNR) conditions than the baseline system using mel-frequency cepstral coefficients. In addition, the proposed method also outperforms the system, which uses auditory-based nonnegative tensor cepstral coefficients [Q. Wu and L. Zhang, "Auditory sparse representation for robust speaker recognition based on tensor structure," EURASIP J. Audio, Speech, Music Process. 2008, 578612 (2008)], in low SNR (≤ 10 dB) conditions.     

U-net网络中融合多头注意力机制的单通道语音增强EI北大核心CSCD

在低信噪比和突发背景噪声条件下,已有的深度学习网络模型在单通道语音增强方面效果并不理想,而人类可以利用语音的长时相关性对不同的语音信号形成综合感知。因此刻画语音的长时依赖关系有助于改进低信噪比和突发背景噪声下的增强性能。受该特性的启发,提出一种融合多头注意力机制和U-net深度网络的增强模型TU-net,实现基于时域的端到端单通道语音增强。TU-net网络模型采用U-net网络的编解码层对带噪语音信号进行多尺度特征融合,并利用多头注意力机制实现双路径Transformer,用于计算语音掩模,更好地建模长时相关性。该模型在时域、时频域和感知域计算损失函数,并通过加权组合损失函数指导训练。仿真实验结果表明,TU-net在低信噪比和突发背景噪声条件下增强语音信号的语音质量感知评估(PESQ)、短时客观可懂度(STOI)和信噪比增益等多个评价指标都优于同类的单通道增强网络模型,且保持相对较少的网络模型参数。     

A new sound coding strategy for suppressing noise in cochlear implants

In the n-of-m strategy, the signal is processed through m bandpass filters from which only the n maximum envelope amplitudes are selected for stimulation. While this maximum selection criterion, adopted in the advanced combination encoder strategy, works well in quiet, it can be problematic in noise as it is sensitive to the spectral composition of the input signal and does not account for situations in which the masker completely dominates the target. A new selection criterion is proposed based on the signal-to-noise ratio (SNR) of individual channels. The new criterion selects target-dominated (SNR > or = 0 dB) channels and discards masker-dominated (SNR<0 dB) channels. Experiment 1 assessed cochlear implant users' performance with the proposed strategy assuming that the channel SNRs are known. Results indicated that the proposed strategy can restore speech intelligibility to the level attained in quiet independent of the type of masker (babble or continuous noise) and SNR level (0-10 dB) used. Results from experiment 2 showed that a 25% error rate can be tolerated in channel selection without compromising speech intelligibility. Overall, the findings from the present study suggest that the SNR criterion is an effective selection criterion for n-of-m strategies with the potential of restoring speech intelligibility.     

采用骨导语音自适应的语句分割方法*

为了解决含噪语句分割问题,也为了解决某些低信噪比环境下传统气导语句分割算法分割效果差、分割准确度低且算法自适应性弱等问题,提出一种基于骨导语音自适应的分段双门限语音分割方法。将骨导语音和气导语音同步采集,获取抗噪性能更好的骨导语音,然后在融合过零率与短时能量中引入随机动态阈值的自适应方法进行端点检测,最后利用分段双门限和语音聚类等手段实现语音分割,提高语音分割算法的鲁棒性。通过实验验证了所提算法的有效性和可行性,同时与其他语音分割算法进行了对比,证明该文所提分割算法精度更高,效果更好。     

基于ERB尺度划分的多子带语声信号抗噪谱减算法

为了研究心理声学在语声增强方面的应用,本文提出了一种基于等效矩阵带宽(ERB)尺度划分的多子带语声信号抗噪谱减算法。此算法根据ERB尺度将带噪信号的频谱划分成多个子带,然后再根据每个子带的分段信噪比以及心理声学掩蔽原则分别计算每个子带的谱减参数,最后在每个子带中分别进行谱减算法处理。实验结果表明,应用新算法所获得的语声增强结果在信噪比、IS失真以及PESQ方面均优于之前提出的多子带语声信号抗噪谱减算法。     

基于听觉模型的耳语音的声韵切分

本文分析了耳语音的特点，并根据生理声学及心理声学的基本理论与实验资料，提出了一种利用听觉模型来进行耳语音声韵切分的方法。这种适用于耳语音声韵切分的听觉感知模型主要分为四个层次：耳蜗对声音频率的分解机理；听觉系统的时域和频域非线性变化；中枢神经系统的侧抑制机理。这种模型能反映在噪声环境下人对低能量语音的听觉感知特性，因而适于耳语音识别，在耳语音声韵母切分实验中得到了满意的结果。